© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 13085
    Prev
    Next
    INDEX
    Explanations

    the start of textual sections or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.64
    Hentet
    -0.63
    .*")]
    -0.57
    رشف
    -0.57
    AnchorTagHelper
    -0.57
    SBATCH
    -0.49
    帖最后由
    -0.48
    WaitGroup
    -0.48
    ГЛА
    -0.46
    Portale
    -0.45
    POSITIVE LOGITS
    :✨
    0.63
    昨日
    0.46
     partielle
    0.42
    eksi
    0.42
    ⎡
    0.42
    '
    0.41
     camiset
    0.41
    fähigkeit
    0.41
    Портали
    0.40
    日前
    0.40
    Activations Density 0.020%

    No Known Activations